Tetsugo Inada

ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks

While recent Vision-Language (VL) models excel at open-vocabulary tasks it is unclear how to use them with specific or uncommon concepts. Personalized Text-to-Image Retrieval (TIR) or Generation (TIG) are recently introduced tasks that represent this challenge where the VL model has to learn a conce…